Ice Prediction Research Articles

Transmission Line Icing Prediction Based on Physically Guided Fast-Slow Transformer

To improve the accuracy of the icing prediction model for overhead transmission lines, a physics-guided Fast-Slow Transformer icing prediction model for overhead transmission lines is proposed, which is based on the icing prediction model with meteorological input characteristics. First, the ice cover data is segmented into different time resolutions through Fourier transform; a transformer model based on Fourier transform is constructed to capture the local and global correlations of the ice cover data; then, according to the calculation model of the comprehensive load on the conductor and the conductor state equation, the variation law of ice thickness, temperature, wind speed, and tension is analyzed, and the model loss function is constructed according to the variation law to guide the training process of the model. Finally, the sample mixing enhancement algorithm is used to reduce the overfitting problem and improve the generalization performance of the prediction model. The results show that the proposed prediction model can consider the mechanical constraints in the ice growth process and accurately capture the dependence between ice cover and meteorology. Compared with traditional prediction models such as LSTM (Long Short-Term Memory) networks, its mean square error, mean absolute error, and mean absolute percentage error are reduced by 0.464–0.674, 0.41–0.53, and 8.87–11.5%, respectively, while the coefficient of determination (R2) is increased by 0.2–0.29.

Ice‐kNN‐South: A Lightweight Machine Learning Model for Antarctic Sea Ice Prediction

Ice‐kNN‐South: A Lightweight Machine Learning Model for Antarctic Sea Ice Prediction

Arctic Sea Ice Prediction Based on Multi‐Scale Graph Modeling With Conservation Laws

AbstractArctic sea ice prediction is critical for exploring climate change, resource extraction, and shipping route planning. This paper introduces a novel neural network model, Ice Graph Attention neTwork (IceGAT), that is trained to predict sea ice concentration (SIC) from a number of atmospheric, oceanic, and land surface measurements. It is based on two design principles: (a) the complex spatial interactions in weather dynamics are captured via a series of graphs corresponding to different spatial resolutions and (b) the incorporation of the physical conservation laws for moisture and potential vorticity. We devise two main variants with 1 hr and 24 hr temporal resolution and determine the optimal input horizon to be 5 days. IceGAT features leading accuracy (96.7%; +2.4% over the current state‐of‐the‐art) and low inference time (1/4 s, on a single GPU). An online implementation (based on data from ERA5) alongside supplementary videos and our shared code are accessible at: https://lannwei.github.io/IceGAT/.

Three-Dimensional Front-Tracking Technique for Multistep Simulations of Aircraft Icing

This paper presents a novel, automatic, level-set-based approach to model three-dimensional boundary problems and generate a new conformal body-fitted mesh. The proposed methodology is applied to long-term in-flight ice accretion, characterized by the formation of extremely irregular ice shapes. The level-set function is defined across the computational volume by comparing the position of the generic volume node with respect to the Lagrangian deformed geometry. This method avoids mesh entanglements and grid intersections typical of mesh deformation techniques, making it suitable for generating a body-fitted discretization of arbitrarily complex geometries as in-flight ice shapes. Effective and tunable smoothing techniques are proposed for dealing with complex ice shapes. Multistep numerical simulations over a horizontal stabilizer with deflected elevator and over a NACA0012 swept wing, both in rime and glaze conditions, are presented. The latter two are also compared with the experimentally measured ice shapes from the first AIAA Ice Prediction Workshop.

An Ensemble Network for High-Accuracy and Long-Term Forecasting of Icing on Wind Turbines.

Freezing of wind turbines causes loss of wind-generated power. Forecasting or prediction of icing on wind turbine blades based on SCADA sensor data allows taking appropriate actions before icing occurs. This paper presents a newly developed deep learning network model named PCTG (Parallel CNN-TCN GRU) for the purpose of high-accuracy and long-term prediction of icing on wind turbine blades. This model combines three networks, the CNN, TCN, and GRU, in order to incorporate both the temporal aspect of SCADA time-series data as well as the dependencies of SCADA variables. The experimentations conducted by using this model and SCADA data from three wind turbines in a wind farm have generated average prediction accuracies of about 97% for prediction horizons of up to 2 days ahead. The developed model is shown to maintain at least 95% prediction accuracy for long prediction horizons of up to 22 days ahead. Furthermore, for another wind farm SCADA dataset, it is shown that the developed PCTG model achieves over 99% icing prediction accuracy 10 days ahead.

CMIP6 Models Underestimate Arctic Sea Ice Loss during the Early Twentieth-Century Warming, despite Simulating Large Low-Frequency Sea Ice Variability

Abstract The variability of Arctic sea ice extent (SIE) on interannual and multidecadal time scales is examined in 29 models with historical forcing participating in phase 6 of the Coupled Model Intercomparison Project (CMIP6) and in twentieth-century sea ice reconstructions. Results show that during the historical period with low external forcing (1850–1919), CMIP6 models display relatively good agreement in their representation of interannual sea ice variability (IVSIE) but exhibit pronounced intermodel spread in multidecadal sea ice variability (MVSIE), which is overestimated with respect to sea ice reconstructions and is dominated by model uncertainty in sea ice simulation in the subpolar North Atlantic. We find that this is associated with differences in models’ sensitivity to Northern Hemispheric sea surface temperatures (SSTs). Additionally, we show that while CMIP6 models are generally capable of simulating multidecadal changes in Arctic sea ice from the mid-twentieth century to present day, they tend to underestimate the observed sea ice decline during the early twentieth-century warming (ETCW; 1915–45). These results suggest the need for an improved characterization of the sea ice response to multidecadal climate variability in order to address the sources of model bias and reduce the uncertainty in future projections arising from intermodel spread. Significance Statement The credibility of Arctic sea ice predictions depends on whether climate models are capable of reproducing changes in the past climate, including patterns of sea ice variability which can mask or amplify the response to global warming. This study aims to better understand how latest-generation global climate models simulate interannual and multidecadal variability of Arctic sea ice relative to available observations. We find that models differ in their representation of multidecadal sea ice variability, which is overall larger than in observations. Additionally, models underestimate the sea ice decline during the period of observed warming between 1915 and 1945. Our results suggest that, to achieve better predictions of Arctic sea ice, the realism of low-frequency sea ice variability in models should be improved.

A Fast Simulation Method for Wind Turbine Blade Icing Integrating Physical Simulation and Statistical Analysis

Simulating wind turbine blade icing quickly is important for wind farms to issue early warnings and effectively deal with the adverse effects of cold weather. However, current numerical simulation methods suffer from high computational costs and lack straightforward acceleration techniques for practical ice prediction. Here, we developed a fast and simple blade icing simulation method via an integrated physical simulation and statistical analysis method. This method consists of two steps: firstly, numerical simulation with CFD, and secondly, table look-up calculations. Over 10,000 sets of wind turbine blade icing simulations based on FENSAP-ICE and an NACA64-A17 wing were conducted to develop this method and analyze the influences of environmental factors on blade icing. The results show that ice thickness generally increases with an increase in wind speed, a decrease in temperature, and an increase in liquid water content (LWC), but there is a nonlinear relationship between them. For example, ice thickness has a linear relationship with the LWC within a certain range but hardly changes with a LWC beyond that range. The validation results show that the fast simulation method established in this paper has good consistency with the original numerical simulation method. It can greatly improve the computational efficiency of icing simulations while retaining the accuracy of numerical simulations. It takes less than 1 s to complete over 1000 sets of icing simulations, which offers potential for the fast prediction of wind turbine blade icing in the future.

An Assessment of Subseasonal Prediction Skill of the Antarctic Sea Ice Edge.

In this study, the subseasonal Antarctic sea ice edge prediction skill of the Copernicus Climate Change Service (C3S) and Subseasonal to Seasonal (S2S) projects was evaluated by a probabilistic metric, the spatial probability score (SPS). Both projects provide subseasonal to seasonal scale forecasts of multiple coupled dynamical systems. We found that predictions by individual dynamical systems remain skillful for up to 38days (i.e., the ECMWF system). Regionally, dynamical systems are better at predicting the sea ice edge in the West Antarctic than in the East Antarctic. However, the seasonal variations of the prediction skill are partly system-dependent as some systems have a freezing-season bias, some had a melting-season bias, and some had a season-independent bias. Further analysis reveals that the model initialization is the crucial prerequisite for skillful subseasonal sea ice prediction. For those systems with the most realistic initialization, the model physics dictates the propagation of initialization errors and, consequently, the temporal length of predictive skill. Additionally, we found that the SPS-characterized prediction skill could be improved by increasing the ensemble size to gain a more realistic ensemble spread. Based on the C3S systems, we constructed a multi-model forecast from the above principles. This forecast consistently demonstrated a superior prediction skill compared to individual dynamical systems or statistical observation-based benchmarks. In summary, our results elucidate the most important factors (i.e., the model initialization and the model physics) affecting the currently available subseasonal Antarctic sea ice prediction systems and highlighting the opportunities to improve them significantly.

An Investigation into Using CFD for the Estimation of Ship Specific Parameters for the SPICE Model for the Prediction of Sea Spray Icing: Part 2—The Verification of SPICE2 with a Full-Scale Test

A hybrid CFD–ML model for the prediction of sea spray icing, SPICE2, was developed in Part 1 of this study in Deshpande et al., 2024. The SPICE2 model is an extension of the ML model, SPICE, where some of the variables required for icing rate predictions: local wind speed, spray duration, spray period, and spray flux, are computed from CFD simulations. These, along with the air and water temperatures, and the salinity from the metocean data are used for the prediction of icing rates at different locations on a moving vessel. The existing full-scale icing measurements proved to be not detailed enough for the purpose of the verification of sea spray icing prediction models and the verification of the SPICE2 required distribution of sea spray icing data on the vessel surface in addition to the vessel design for simulation. A full-scale sea spray icing test was conducted in 2018 by Sundsbø et al. on a fully enclosed lifeboat equipped for the Goliat field in the Barents Sea. The 3D design of the same lifeboat, together with the corresponding metocean conditions and ship characteristics was used for the simulation of the vessel-specific parameters required for the verification of the icing rate and distribution prediction from the SPICE2 model against the measured distribution of sea spray icing rates on the lifeboat surface. The availability of the 3D model of this lifeboat, in addition to the fact that the icing measurements from this test were detailed enough to attempt a model verification served the purpose of validating the SPICE2 model. The icing rates measured on this lifeboat are used for the full-scale validation of the SPICE2 model that is proposed in Part 1 of this study. It was seen that the icing rates predicted by SPICE2 concurred with 9 of 13 selected locations on the lifeboat. The ones which did not showed very little deviation from the measurements. The icing rate and distribution prediction with SPICE2 were satisfactorily validated against full-scale icing measurements. This is a first attempt in modelling sea spray generation using CFD and further research into CFD for the estimation of spray flux is suggested.

Investigation into Using CFD for Estimation of Ship Specific Parameters for the SPICE Model for Prediction of Sea Spray Icing: Part 1—The Proposal

Investigation into Using CFD for Estimation of Ship Specific Parameters for the SPICE Model for Prediction of Sea Spray Icing: Part 1—The Proposal

Research on wind turbine icing prediction data processing and accuracy of machine learning algorithm

Studying the icing problem of wind turbine blades is crucial for optimizing wind farm operation and maintenance. Traditional machine learning algorithms like Random Forest and Support Vector Machines have limitations in handling complex time series data and capturing long-term dependencies, leading to insufficient accuracy and generalization. To address these gaps, this paper proposes a comprehensive approach involving advanced machine learning frameworks and feature engineering techniques. This paper based on the original SACDA dataset, four distinct types of processing are performed on the prediction data via PCA dimensionality reduction and the introduction of new features; meanwhile, the four types mentioned above of datasets are trained and predicted using the Gated Recycling Unit model (GRU), Random Forest (RF), GA-BP Neural Network (BP), and Extreme Learning Machine (ELM) models. The results indicate that the prediction accuracies of all four types of models are more satisfactory, with the RF model having the highest prediction accuracy and the overall accuracy remaining above 99 percent, the dataset + RF model after dimensionality reduction of the original sensitive features having the highest prediction accuracy and speed.

High-resolution regional sea-ice model based on the discrete element method with boundary conditions from a large-scale model for ice drift

Abstract Understanding sea-ice dynamics at the floe scale is crucial to comprehend polar climate systems. While continuum models are commonly used to simulate large-scale sea-ice dynamics, they have limitations in accurately representing sea-ice behaviour at small scales. DEMs, on the other hand, are well-suited for modelling the behaviour of individual ice floes but face limitations due to computational constraints. To address the limitations of both approaches while combining their strengths, we explored the feasibility of using a DEM within a continuum model, where the latter provides boundary conditions for a rectangular high-resolution DEM domain. This paper presents a feasibility study where a discrete model of a 100 × 100 km2 icefield was created using high-resolution optical satellite imagery. Sea-ice dynamics were simulated in the DEM considering environmental forces and integrating large-scale ice-drift velocities as boundary conditions. Model predictions were compared with satellite observations for ice drift and deformation parameters. This numerical approach showed potential for offering accurate, high-resolution predictions of sea ice, particularly in coastal areas and near islands, and may find applications in ice navigation and climate studies. However, further development of the DEM, along with upgrades to the coupled ocean models providing data for the ice component, may be necessary. Additionally, challenges remain to develop a two-way coupling between the DEM and a continuum model, which may be needed to improve the accuracy of large-scale simulations.

Wind Farm Prediction of Icing Based on SCADA Data

In cold climates, ice formation on wind turbines causes power reduction produced by a wind farm. This paper introduces a framework to predict icing at the farm level based on our recently developed Temporal Convolutional Network prediction model for a single turbine using SCADA data.First, a cross-validation study is carried out to evaluate the extent predictors trained on a single turbine of a wind farm can be used to predict icing on the other turbines of a wind farm. This fusion approach combines multiple turbines, thereby providing predictions at the wind farm level. This study shows that such a fusion approach improves prediction accuracy and decreases fluctuations across different prediction horizons when compared with single-turbine prediction. Two approaches are considered to conduct farm-level icing prediction: decision fusion and feature fusion. In decision fusion, icing prediction decisions from individual turbines are combined in a majority voting manner. In feature fusion, features of individual turbines are averaged first before conducting prediction. The results obtained indicate that both the decision fusion and feature fusion approaches generate farm-level icing prediction accuracies that are 7% higher with lower standard deviations or fluctuations across different prediction horizons when compared with predictions for a single turbine.

Southern Ocean Ice Prediction System version 1.0 (SOIPS v1.0): description of the system and evaluation of synoptic-scale sea ice forecasts

Abstract. An operational synoptic-scale sea ice forecasting system for the Southern Ocean, namely the Southern Ocean Ice Prediction System (SOIPS), has been developed to support ship navigation in the Antarctic sea ice zone. Practical application of the SOIPS forecasts had been implemented for the 38th Chinese National Antarctic Research Expedition for the first time. The SOIPS is configured on an Antarctic regional sea ice–ocean–ice shelf coupled model and an ensemble-based localized error subspace transform Kalman filter data assimilation model. Daily near-real-time satellite sea ice concentration observations are assimilated into the SOIPS to update sea ice concentration and thickness in the 12 ensemble members of the model state. By evaluating the SOIPS performance in forecasting sea ice metrics in a complete melt–freeze cycle from 1 October 2021 to 30 September 2022, this study shows that the SOIPS can provide reliable Antarctic sea ice forecasts. In comparison with non-assimilated EUMETSAT Ocean and Sea Ice Satellite Application Facility (OSI SAF) data, annual mean root mean square errors in the sea ice concentration forecasts at a lead time of up to 168 h are lower than 0.19, and the integrated ice edge errors in the sea ice forecasts in most freezing months at lead times of 24 and 72 h maintain around 0.5×106 km2 and below 1.0×106 km2, respectively. With respect to the scarce Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) observations, the mean absolute errors in the sea ice thickness forecasts at a lead time of 24 h are lower than 0.3 m, which is in the range of the ICESat-2 uncertainties. Specifically, the SOIPS has the ability to forecast sea ice drift, in both magnitude and direction. The derived sea ice convergence rate forecasts have great potential for supporting ship navigation on a fine local scale. The comparison between the persistence forecasts and the SOIPS forecasts with and without data assimilation further shows that both model physics and the data assimilation scheme play important roles in producing reliable sea ice forecasts in the Southern Ocean.

Winter arctic sea ice volume decline: uncertainties reduced using passive microwave-based sea ice thickness

Arctic sea ice volume (SIV) is a key climate indicator and memory source in sea ice predictions and projections, yet suffering from large observational and model uncertainty. Here, we test whether passive microwave (PMW) data constrain the long-term evolution of Arctic SIV, as recently hypothesized. We find many commonalities in Arctic SIV changes from a PMW sea ice thickness (SIT) 1992-2020 time series reconstructed with a neural network algorithm trained on lidar altimetry, and the reference PIOMAS reanalysis: relatively low differences in SIV mean (4615 km3, 37%), SIV trends (46 km3, 17%), and phased variability (r2=0.55). Key to reduced differences is the consistent evolution of many SIV contributors: seasonal and perennial ice coverage, their SIT contrast, whereas perennial SIT provides the largest remaining uncertainty source. We argue that PMW includes useful SIT information, reducing SIV uncertainty. We foresee progress from sea ice reanalyses combining dynamical models and data assimilation of PMW SIT estimates, in addition to the already assimilated PWM sea ice concentration.

Aircraft ice accretion prediction based on geometrical constraints enhancement neural networks

PurposeThe purpose of this study is to establish a novel airfoil icing prediction model using deep learning with geometrical constraints, called geometrical constraints enhancement neural networks, to improve the prediction accuracy compared to the non-geometrical constraints model.Design/methodology/approachThe model is developed with flight velocity, ambient temperature, liquid water content, median volumetric diameter and icing time taken as inputs and icing thickness given as outputs. To enhance the icing prediction accuracy, the model involves geometrical constraints into the loss function. Then the model is trained according to icing samples of 2D NACA0012 airfoil acquired by numerical simulation.FindingsThe results show that the involvement of geometrical constraints effectively enhances the prediction accuracy of ice shape, by weakening the appearance of fluctuation features. After training, the airfoil icing prediction model can be used for quickly predicting airfoil icing.Originality/valueThis work involves geometrical constraints in airfoil icing prediction model. The proposed model has reasonable capability in the fast assessment of aircraft icing.

Modeling pan-Arctic seasonal and interannual landfast sea ice thickness and snow depth between 1979 and 2021

ABSTRACT Landfast sea ice (LFSI) is sensitive to local climate change, making it an important component of the cryosphere system. In this study, the LFSI around the pan-Arctic domain was simulated from 1979 to 2021 using a well-validated snow and ice thermodynamic model (HIGHTSI) under the framework of the Fast Ice Prediction System (FIPS), forced by the ERA5 reanalysis. The simulation results agree well with the in-situ observations in the Canadian Arctic, with a mean error of −0.06 ± 0.29 m for ice thickness and −0.04 ± 0.12 m for snow depth. A decrease of −2.8 ± 0.4 cm/10a in thickness and −16.2 ± 1.5 km3/a in volume for the Arctic LFSI was modeled during this period. There was significant spatial variability among the different domains, with the fastest decline found in the Vilkitsky Strait. The modeled snow depth shows large interannual and spatial variations, which was confirmed by other modeling results. The spatiotemporal variations in both air temperature and precipitation are the driving factors for the multi-decadal variations in LFSI thickness. The decreasing air temperature during the 2010s aligned with a slower thickness decrease and a slight volume increase for LFSI, which agreed with the pan-Arctic sea ice pattern.

Predicting September Arctic Sea Ice: A Multimodel Seasonal Skill Comparison

Abstract This study quantifies the state of the art in the rapidly growing field of seasonal Arctic sea ice prediction. A novel multimodel dataset of retrospective seasonal predictions of September Arctic sea ice is created and analyzed, consisting of community contributions from 17 statistical models and 17 dynamical models. Prediction skill is compared over the period 2001–20 for predictions of pan-Arctic sea ice extent (SIE), regional SIE, and local sea ice concentration (SIC) initialized on 1 June, 1 July, 1 August, and 1 September. This diverse set of statistical and dynamical models can individually predict linearly detrended pan-Arctic SIE anomalies with skill, and a multimodel median prediction has correlation coefficients of 0.79, 0.86, 0.92, and 0.99 at these respective initialization times. Regional SIE predictions have similar skill to pan-Arctic predictions in the Alaskan and Siberian regions, whereas regional skill is lower in the Canadian, Atlantic, and central Arctic sectors. The skill of dynamical and statistical models is generally comparable for pan-Arctic SIE, whereas dynamical models outperform their statistical counterparts for regional and local predictions. The prediction systems are found to provide the most value added relative to basic reference forecasts in the extreme SIE years of 1996, 2007, and 2012. SIE prediction errors do not show clear trends over time, suggesting that there has been minimal change in inherent sea ice predictability over the satellite era. Overall, this study demonstrates that there are bright prospects for skillful operational predictions of September sea ice at least 3 months in advance.

Reconstruction of Arctic Sea Ice Thickness and Its Impact on Sea Ice Forecasting in the Melting Season

Abstract Generally, sea ice prediction skills can be improved by assimilating available observations of the sea ice concentration (SIC) and sea ice thickness (SIT) into a numerical forecast model to update the initial conditions. However, due to inadequate daily SIT satellite observations in the Arctic melting season, the SIC fields in forecast models are usually directly updated, which causes mismatch of SIC and SIT in dynamics and affects the model prediction accuracy. In this study, a statistically based bivariate regression model of SIT (BRMT) is tentatively established based on the grid reanalysis data of SIC and SIT to reconstruct daily Arctic SIT data. The results show that the BRMT can reproduce the spatial and temporal changes in the SIT in the melting season and capture the variation trend of SIT in some periods. Compared with the SIT observations from buoy and satellite, the reconstructed SIT shows better performance in the central Arctic than other datasets. Furthermore, when the reconstructed SIT is added to the forecast model with only assimilated SIC, the forecast accuracy of SIC, sea ice extent, and SIT in the Arctic melting season is improved and does not weaken with the increase in the forecast time. Especially in the central Arctic, the average absolute deviation between 24-h SIT forecast results and observations is only 0.16 m. The results indicate great potential for applying the reconstructed SIT to the operational forecast of Arctic sea ice during the melting season in the future. Significance Statement To improve the prediction skills of Arctic sea ice, it is necessary to assimilate the sea ice observation into the dynamic model to generate a more realistic initial prediction field. At present, the observation data of daily sea ice thickness (SIT) during the Arctic melting season are few, which cannot well meet the demand of operational SIT forecast. In this study, a bivariate regression model is put forward to construct SIT using the sea ice concentration (SIC) observation. Benefitting from the joint assimilation of the observed SIC and the reconstructed SIT, the forecast accuracy of sea ice variables is greatly improved. The reconstructed SIT is expected to provide an available dataset for further research on the Arctic sea ice forecast.

A metaheuristic-optimization-based neural network for icing prediction on transmission lines

Ice accretion on overhead transmission line systems is a leading cause of power outages and can lead to substantial economic losses in northern regions. Therefore, accurately and rapidly predicting ice accretion on power lines is crucial for ensuring the safe operation of the power grid. This study introduces a machine learning method for predicting the ice-to-liquid ratio (ILR), an important parameter for assessing ice accretion efficiency. While estimating ILR is vital for operational forecasting, many existing ice accretion models do not include this capability. A feedforward neural network (FFNN) trained with stochastic gradient descent and various metaheuristic optimizers - specifically particle swarm optimization, grey wolf optimizer, whale optimizer, and slime mold optimizer - is employed to forecast hourly ILR. Environmental data required for training and testing the FFNN model were obtained from the Automated Surface Observing System (ASOS). A global sensitivity analysis using the Sobol index, evaluated via the coefficients of a polynomial chaos expansion, was conducted to identify the most influential input parameters. The results indicate that only four input parameters significantly contribute to the variance in the response: precipitation, temperature, dew point temperature, and wind speed. Furthermore, the FFNN model trained with metaheuristic optimizers outperformed the stochastic gradient descent approach. With the predicted ILR, ice accumulation can be easily calculated as the product of ILR and the amount of liquid precipitation depth.